Train and save a LoRA Style
Changed onTrains a LoRA through the same dataset preparation, captioning defaults, authorization, billing and saved Style lifecycle as the web Train dialog. Upload image files through the assets API first, then pass their Flora URLs. Returns a run_id for GET /runs/{runId} and style_id for GET /loras/{styleId}; use the ready style_id as params.lora_id with a compatible inference model. Training spends workspace usage. Persist client_token before dispatch and reuse it with identical inputs to recover a lost response. The optional Idempotency-Key header separately rejects duplicate HTTP requests for two hours with idempotency_duplicate.
Request
- Base URLhttps://app.flora.ai/api/v1
- URLhttps://app.flora.ai/api/v1/loras/train
- AuthHTTP bearer
Request body
Example request
{
"workspace_id": "ws_abc123",
"project_id": "prj_abc123"
}Response
Training accepted, or the existing request recovered.
Example response
{
"style_id": "sty_abc123",
"run_id": "run_abc123",
"workspace_id": "ws_abc123",
"project_id": "prj_abc123"
}Changes
- warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status - warning
added the new
not_configuredenum value to the/response property for the response status
- warning
- info
endpoint added
- info